Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1084 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.7235. Min Act: -0.0001

Data Index: 984781 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.7244. Min Act: -0.0001

Data Index: 707027 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5899. Min Act: -0.0001

Data Index: 121042 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6226. Min Act: -0.0001

Data Index: 700345 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5673. Min Act: -0.0001

Data Index: 54672 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6563. Min Act: -0.0001

Data Index: 318446 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5988. Min Act: -0.0001

Data Index: 1094430 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6139. Min Act: -0.0001

Data Index: 1254719 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6169. Min Act: -0.0001

Data Index: 988851 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5197. Min Act: -0.0001

Data Index: 858593 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6030. Min Act: -0.0001

Data Index: 900549 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5326. Min Act: -0.0001

Data Index: 199890 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5604. Min Act: -0.0001

Data Index: 1211589 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6122. Min Act: -0.0001

Data Index: 559184 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5089. Min Act: -0.0001

Data Index: 985610 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.6684. Min Act: -0.0001

Data Index: 442098 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5248. Min Act: -0.0001

Data Index: 130824 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.5402. Min Act: -0.0001

Data Index: 543093 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4112. Min Act: -0.0001

Data Index: 210148 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.7244. Min Range: -1.7244

Max Act: 1.4859. Min Act: -0.0001

Data Index: 408953 (C4 (Web Text))

Max Activating Token Index: 202